Dealing with Ambiguity in Robotic Grasping via Multiple Predictions
원문 초록
Humans excel in grasping and manipulating objects because of their life-long experience and knowledge about the 3D shape and weight distribution of objects. However, the lack of such intuition in robots makes robotic grasping an exceptionally challenging task. There are often several equally viable options of grasping an object. However, this ambiguity is not modeled in conventional systems that estimate a single, optimal grasp position. We propose to tackle this problem by simultaneously estimating multiple grasp poses from a single RGB image of the target object. Further, we reformulate the problem of robotic grasping by replacing conventional grasp rectangles with grasp belief maps, which hold more precise location information than a rectangle and account for the uncertainty inherent to the task. We augment a fully convolutional neural network with a multiple hypothesis prediction model that predicts a set of grasp hypotheses in under 60ms, which is critical for real-time robotic applications. The grasp detection accuracy reaches over 90% for unseen objects, outperforming the current state of the art on this task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception
Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation
A Benchmarking Study of Vision-based Robotic Grasping Algorithms
Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
Supertoroid fitting of objects with holes for robotic grasping and scene generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.